Created by: boceng

使用docker编译得到paddle_serving_server_gpu-0.2.2-py3-none-any.whl，在docker外进行安装后，启动服务报错： CUDA not found, please check your environment or use cpu version by "pip install paddle_serving_server"

但在docker内进行安装并启动服务不会报错，启动结果如下：

Use local bin : /paddle/ServingCuda10-1/build/core/general-server/serving
Going to Run Comand
/paddle/ServingCuda10-1/build/core/general-server/serving -enable_model_toolkit -inferservice_path workdir_0 -inferservice_file infer_service.prototxt -max_concurrency 0 -num_threads 10 -port 9493 -reload_interval_s 10 -resource_path workdir_0 -resource_file resource.prototxt -workflow_path workdir_0 -workflow_file workflow.prototxt -bthread_concurrency 10 -gpuid 0 -max_body_size 536870912 
I0100 00:00:00.000000 11626 op_repository.h:65] RAW: Succ regist op: GeneralDistKVInferOp
I0100 00:00:00.000000 11626 op_repository.h:65] RAW: Succ regist op: GeneralReaderOp
I0100 00:00:00.000000 11626 op_repository.h:65] RAW: Succ regist op: GeneralDistKVQuantInferOp
I0100 00:00:00.000000 11626 op_repository.h:65] RAW: Succ regist op: GeneralResponseOp
I0100 00:00:00.000000 11626 op_repository.h:65] RAW: Succ regist op: GeneralTextReaderOp
I0100 00:00:00.000000 11626 op_repository.h:65] RAW: Succ regist op: GeneralTextResponseOp
I0100 00:00:00.000000 11626 op_repository.h:65] RAW: Succ regist op: GeneralInferOp
I0100 00:00:00.000000 11626 op_repository.h:65] RAW: Succ regist op: GeneralCopyOp
I0100 00:00:00.000000 11626 service_manager.h:61] RAW: Service[LoadGeneralModelService] insert successfully!
I0100 00:00:00.000000 11626 load_general_model_service.pb.h:299] RAW: Success regist service[LoadGeneralModelService][PN5baidu14paddle_serving9predictor26load_general_model_service27LoadGeneralModelServiceImplE]
I0100 00:00:00.000000 11626 service_manager.h:61] RAW: Service[GeneralModelService] insert successfully!
I0100 00:00:00.000000 11626 general_model_service.pb.h:1473] RAW: Success regist service[GeneralModelService][PN5baidu14paddle_serving9predictor13general_model23GeneralModelServiceImplE]
I0100 00:00:00.000000 11626 factory.h:121] RAW: Succ insert one factory, tag: FLUID_GPU_ANALYSIS, base type N5baidu14paddle_serving9predictor11InferEngineE
W0100 00:00:00.000000 11626 fluid_gpu_engine.cpp:27] RAW: Succ regist factory: ::baidu::paddle_serving::predictor::FluidInferEngine<FluidGpuAnalysisCore>->::baidu::paddle_serving::predictor::InferEngine, tag: FLUID_GPU_ANALYSIS in macro!
I0100 00:00:00.000000 11626 factory.h:121] RAW: Succ insert one factory, tag: FLUID_GPU_ANALYSIS_DIR, base type N5baidu14paddle_serving9predictor11InferEngineE
W0100 00:00:00.000000 11626 fluid_gpu_engine.cpp:33] RAW: Succ regist factory: ::baidu::paddle_serving::predictor::FluidInferEngine< FluidGpuAnalysisDirCore>->::baidu::paddle_serving::predictor::InferEngine, tag: FLUID_GPU_ANALYSIS_DIR in macro!
I0100 00:00:00.000000 11626 factory.h:121] RAW: Succ insert one factory, tag: FLUID_GPU_ANALYSIS_DIR_SIGMOID, base type N5baidu14paddle_serving9predictor11InferEngineE
W0100 00:00:00.000000 11626 fluid_gpu_engine.cpp:39] RAW: Succ regist factory: ::baidu::paddle_serving::predictor::FluidInferEngine< FluidGpuAnalysisDirWithSigmoidCore>->::baidu::paddle_serving::predictor::InferEngine, tag: FLUID_GPU_ANALYSIS_DIR_SIGMOID in macro!
I0100 00:00:00.000000 11626 factory.h:121] RAW: Succ insert one factory, tag: FLUID_GPU_NATIVE, base type N5baidu14paddle_serving9predictor11InferEngineE
W0100 00:00:00.000000 11626 fluid_gpu_engine.cpp:44] RAW: Succ regist factory: ::baidu::paddle_serving::predictor::FluidInferEngine<FluidGpuNativeCore>->::baidu::paddle_serving::predictor::InferEngine, tag: FLUID_GPU_NATIVE in macro!
I0100 00:00:00.000000 11626 factory.h:121] RAW: Succ insert one factory, tag: FLUID_GPU_NATIVE_DIR, base type N5baidu14paddle_serving9predictor11InferEngineE
W0100 00:00:00.000000 11626 fluid_gpu_engine.cpp:49] RAW: Succ regist factory: ::baidu::paddle_serving::predictor::FluidInferEngine<FluidGpuNativeDirCore>->::baidu::paddle_serving::predictor::InferEngine, tag: FLUID_GPU_NATIVE_DIR in macro!
I0100 00:00:00.000000 11626 factory.h:121] RAW: Succ insert one factory, tag: FLUID_GPU_NATIVE_DIR_SIGMOID, base type N5baidu14paddle_serving9predictor11InferEngineE
W0100 00:00:00.000000 11626 fluid_gpu_engine.cpp:55] RAW: Succ regist factory: ::baidu::paddle_serving::predictor::FluidInferEngine< FluidGpuNativeDirWithSigmoidCore>->::baidu::paddle_serving::predictor::InferEngine, tag: FLUID_GPU_NATIVE_DIR_SIGMOID in macro!
I0100 00:00:00.000000 11626 factory.h:121] RAW: Succ insert one factory, tag: FLUID_CPU_ANALYSIS, base type N5baidu14paddle_serving9predictor11InferEngineE
W0100 00:00:00.000000 11626 fluid_cpu_engine.cpp:25] RAW: Succ regist factory: ::baidu::paddle_serving::predictor::FluidInferEngine<FluidCpuAnalysisCore>->::baidu::paddle_serving::predictor::InferEngine, tag: FLUID_CPU_ANALYSIS in macro!
I0100 00:00:00.000000 11626 factory.h:121] RAW: Succ insert one factory, tag: FLUID_CPU_ANALYSIS_DIR, base type N5baidu14paddle_serving9predictor11InferEngineE
W0100 00:00:00.000000 11626 fluid_cpu_engine.cpp:31] RAW: Succ regist factory: ::baidu::paddle_serving::predictor::FluidInferEngine< FluidCpuAnalysisDirCore>->::baidu::paddle_serving::predictor::InferEngine, tag: FLUID_CPU_ANALYSIS_DIR in macro!
I0100 00:00:00.000000 11626 factory.h:121] RAW: Succ insert one factory, tag: FLUID_CPU_ANALYSIS_DIR_SIGMOID, base type N5baidu14paddle_serving9predictor11InferEngineE
W0100 00:00:00.000000 11626 fluid_cpu_engine.cpp:37] RAW: Succ regist factory: ::baidu::paddle_serving::predictor::FluidInferEngine< FluidCpuAnalysisDirWithSigmoidCore>->::baidu::paddle_serving::predictor::InferEngine, tag: FLUID_CPU_ANALYSIS_DIR_SIGMOID in macro!
I0100 00:00:00.000000 11626 factory.h:121] RAW: Succ insert one factory, tag: FLUID_CPU_NATIVE, base type N5baidu14paddle_serving9predictor11InferEngineE
W0100 00:00:00.000000 11626 fluid_cpu_engine.cpp:42] RAW: Succ regist factory: ::baidu::paddle_serving::predictor::FluidInferEngine<FluidCpuNativeCore>->::baidu::paddle_serving::predictor::InferEngine, tag: FLUID_CPU_NATIVE in macro!
I0100 00:00:00.000000 11626 factory.h:121] RAW: Succ insert one factory, tag: FLUID_CPU_NATIVE_DIR, base type N5baidu14paddle_serving9predictor11InferEngineE
W0100 00:00:00.000000 11626 fluid_cpu_engine.cpp:47] RAW: Succ regist factory: ::baidu::paddle_serving::predictor::FluidInferEngine<FluidCpuNativeDirCore>->::baidu::paddle_serving::predictor::InferEngine, tag: FLUID_CPU_NATIVE_DIR in macro!
I0100 00:00:00.000000 11626 factory.h:121] RAW: Succ insert one factory, tag: FLUID_CPU_NATIVE_DIR_SIGMOID, base type N5baidu14paddle_serving9predictor11InferEngineE
W0100 00:00:00.000000 11626 fluid_cpu_engine.cpp:53] RAW: Succ regist factory: ::baidu::paddle_serving::predictor::FluidInferEngine< FluidCpuNativeDirWithSigmoidCore>->::baidu::paddle_serving::predictor::InferEngine, tag: FLUID_CPU_NATIVE_DIR_SIGMOID in macro!
WARNING: Logging before InitGoogleLogging() is written to STDERR
I0601 13:35:24.102823 11626 pdserving.cpp:109] use configure[workdir_0/infer_service.prototxt] port[9493] instead of flags
I0601 13:35:24.959201 11626 init.cc:66] Init commandline: dummy dummy --fraction_of_gpu_memory_to_use=0.006855 --cudnn_deterministic=True 
I0601 13:35:24.959260 11626 analysis_predictor.cc:84] Profiler is deactivated, and no profiling report will be generated.
I0601 13:35:24.974730 11626 analysis_predictor.cc:833] MODEL VERSION: 1.7.1
I0601 13:35:24.974745 11626 analysis_predictor.cc:835] PREDICTOR VERSION: 1.7.2
I0601 13:35:24.975145 11626 analysis_predictor.cc:440] ir_optim is turned off, no IR pass will be executed
--- Running analysis [ir_graph_build_pass]
--- Running analysis [ir_graph_clean_pass]
--- Running analysis [ir_analysis_pass]
--- Running analysis [ir_params_sync_among_devices_pass]
I0601 13:35:25.131299 11626 ir_params_sync_among_devices_pass.cc:41] Sync params from CPU to GPU
--- Running analysis [adjust_cudnn_workspace_size_pass]
--- Running analysis [inference_op_replace_pass]
--- Running analysis [ir_graph_to_program_pass]
I0601 13:35:25.299015 11626 analysis_predictor.cc:462] ======= optimize end =======
I0601 13:35:25.302732 11626 fluid_gpu_engine.h:215] create paddle predictor sucess, path: /paddle/PaddleDetection/paddle/paddleDetection/PaddleDetection/servingExport/faster_rcnn_r101_1x/serving_client
W0601 13:35:25.302754 11626 infer.h:487] Succ load common model[0x20a99540], path[/paddle/PaddleDetection/paddle/paddleDetection/PaddleDetection/servingExport/faster_rcnn_r101_1x/serving_client].
W0601 13:35:25.302768 11626 infer.h:185] Succ load model_data_path/paddle/PaddleDetection/paddle/paddleDetection/PaddleDetection/servingExport/faster_rcnn_r101_1x/serving_client
I0601 13:35:25.302775 11626 infer.h:612] FLGS_logtostderr 1

-------------------------------------分割线-----------------------------------------

docker内编译设置有：Dockerfile.gpu.devel下第一行为 FROM nvidia/cuda:10.0-cudnn7-devel-centos7，docker内部cuda版本为CUDA Version 10.0.130，docker外部cuda版本同样为CUDA Version 10.0.130，剩余操作均遵循文档步骤。

请问如何解决，感谢~